Plant Breeding Evaluation with Rank Entropy-based Decision Tree

摘要: Abstract: With the rapid development of breeding equipments, large scale becomes possible, massive data evaluation has to be done by software automatically. In this circumstance, paper tries evaluate variety with collected informative through mining technologies. According characteristics, plant is considered as an ordinal classification task, and a rank entropy-based decision tree algorithm proposed do classification. The uses historical trait phenotype construct trees, which are then used generate evaluations for future cultivars their phenotype. To demonstrate effectiveness, experiments carried out on three groups soybean comparison tests (early-maturity, medium-maturity, green soybean). This work can free breeders from number basic while increase efficiency breeding.